Why in different execution different performance comes in the Neural Network same program ?

Why in different execution different performance comes in the Neural Network same program ?

Answer 1

[Greg Heath]

The state of the RNG is different. Therefore the random initial weights and random trn/val/tst data divisions are different.

For examples of initializing the RNG so that runs can be duplicated try searching on

 greg rng(4151941)

 greg rng(0)

 greg rng('default')

[Deep Gogoi]

Can I make the performance value for every execution. If it is possible what i ave to do in coding ?

[Greg Heath]

If you set the RNG to the same state before the 1st random number assignment, the runs will be duplicated.

Did you perform the 3 searches I recommended?

[Deep Gogoi]

Sir, I have attached my Matlab code and dataset file . Can You check and guide me to make constant performance for every execution

[Greg Heath]

You wouldn't have to post your data for me to do your work if you had performed the searches I recommended.